Title: Machine Learning for Sciences — Nonlinear Feature Selection for High-Dimensional Data
Speaker: Makoto Yamada
Time: 9: 00-11: 00, Monday, 15 October, 2018
Venue: Multi-function Hall, 2nd Floor, Dongrong Conference Center, Central Campus
Organizer: School of Artificial Intelligence, International Center of Future Science
Abstract:
Feature selection is an important machine learning problem. However, there are a few methods that can select features from large and ultra high-dimensional data (more than a million features) in a nonlinear way. In this talk, we first introduce a Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) that can efficiently select non-redundant features from small and high-dimensional data in a nonlinear way. A key advantage of HSIC Lasso is that it is a convex method and can find a globally optimal solution. Then we further extend the proposed method to handle ultra high-dimensional data by incorporating with distributed computing framework. Moreover, we introduce two newly proposed algorithms the localized lasso and hsicInf, where the localized lasso is useful for selecting a set of features from each sub-cluster and hsicInf can obtain p-values of selected features from any type of data.
Biography:
Dr. Makoto Yamada is currently an Associate Professor at Kyoto University and head of RIKEN AIP. He obtained his Master’s Degree in Electrical Engineering from Colorado State University, Fort Collins, the USA in 2005 and his Doctoral Degree in The Graduate University for Advanced Studies, Japan in 2010. He has served as a postdoctoral researcher at the Tokyo Institute of Technology, a researcher at NTT Communication Science Laboratory, and a research scientist at Yahoo Labs. His research areas include Machine Learning, Natural Language Processing, Signal Processing, and Computer Vision. In recent years, more than 30 research papers have been published in top conferences and journals. He won the Best Paper Award of WSDM in 2016 and published a paper in Cell in 2018.
